Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step problem solving.
Modalities
In / Out Price
$0.375 / $1.875per 1M
Context
1.0M
Released
Aug 13, 2026
This model is hosted by one provider. OpenRouter forwards every request to it directly — no routing decisions to make.
The average price customers actually pay for this model, next to the prices providers post. Caching and discounts mean the price actually paid is often well below the listed one.
Throughput is how fast the model writes (tokens per second — higher is better). Latency is total round-trip time (lower is better). TTFT is time-to-first-token — how long before you see anything appear (lower is better).
Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.
Scores on standardized evaluations. Higher percentages are better — and rank percentile shows where this model lands among all models on OpenRouter.
| Source | Benchmark | Score |
|---|---|---|
| Artificial Analysis | Gemini 3.7 Flash (low) Coding Index | 71.0 |
| Artificial Analysis | Gemini 3.7 Flash (low) GPQA Diamond | 90.1% |
| Artificial Analysis | Gemini 3.7 Flash (low) HLE | 35.1% |
| Artificial Analysis | Gemini 3.7 Flash (low) AA-LCR | 78.7% |
| Artificial Analysis | Gemini 3.7 Flash (low) GDPval-AA | 42.7% |
| Artificial Analysis | Gemini 3.7 Flash (low) CritPt | 5.7% |
| Artificial Analysis | Gemini 3.7 Flash (low) SciCode | 55.7% |
| Artificial Analysis | Gemini 3.7 Flash (low) AA-Omniscience Accuracy | 53.6% |
| Artificial Analysis | Gemini 3.7 Flash (low) AA-Omniscience Non-Hallucination Rate | 32.3% |
| Artificial Analysis | Gemini 3.7 Flash (medium) Coding Index | 71.5 |
| Artificial Analysis | Gemini 3.7 Flash (medium) GPQA Diamond | 92.1% |
| Artificial Analysis | Gemini 3.7 Flash (medium) HLE | 39.0% |
| Artificial Analysis | Gemini 3.7 Flash (medium) AA-LCR | 83.0% |
| Artificial Analysis | Gemini 3.7 Flash (medium) GDPval-AA | 45.3% |
| Artificial Analysis | Gemini 3.7 Flash (medium) CritPt | 9.4% |
| Artificial Analysis | Gemini 3.7 Flash (medium) SciCode | 59.8% |
| Artificial Analysis | Gemini 3.7 Flash (medium) AA-Omniscience Accuracy | 54.0% |
| Artificial Analysis | Gemini 3.7 Flash (medium) AA-Omniscience Non-Hallucination Rate | 34.1% |
| Artificial Analysis | Gemini 3.7 Flash (high) Intelligence Index | 39.4 |
| Artificial Analysis | Gemini 3.7 Flash (high) Coding Index | 76.1 |
| Artificial Analysis | Gemini 3.7 Flash (high) Agentic Index | 36.4 |
| Artificial Analysis | Gemini 3.7 Flash (high) GPQA Diamond | 94.5% |
| Artificial Analysis | Gemini 3.7 Flash (high) HLE | 47.9% |
| Artificial Analysis | Gemini 3.7 Flash (high) AA-LCR | 81.7% |
| Artificial Analysis | Gemini 3.7 Flash (high) GDPval-AA | 46.7% |
| Artificial Analysis | Gemini 3.7 Flash (high) CritPt | 14.3% |
| Artificial Analysis | Gemini 3.7 Flash (high) SciCode | 57.2% |
| Artificial Analysis | Gemini 3.7 Flash (high) AA-Omniscience Accuracy | 55.3% |
| Artificial Analysis | Gemini 3.7 Flash (high) AA-Omniscience Non-Hallucination Rate | 35.5% |
| Design Arena | Gemini 3.7 Flash Agents Arena Agenticgamedev Elo | 1235 |
| Design Arena | Gemini 3.7 Flash Agents Arena Androidnative Elo | 1252 |
| Design Arena | Gemini 3.7 Flash Agents Arena Full Stack Elo | 1223 |
| Design Arena | Gemini 3.7 Flash Agents Arena Mobile Apps Elo | 1260 |
| Design Arena | Gemini 3.7 Flash Agents Arena Webapps Elo | 1235 |
| Design Arena | Gemini 3.7 Flash Models Arena 3D Elo | 1336 |
| Design Arena | Gemini 3.7 Flash Models Arena Asciiart Elo | 1267 |
| Design Arena | Gemini 3.7 Flash Models Arena Code Categories Elo | 1323 |
| Design Arena | Gemini 3.7 Flash Models Arena Data Visualization Elo | 1325 |
| Design Arena | Gemini 3.7 Flash Models Arena Game Development Elo | 1350 |
| Design Arena | Gemini 3.7 Flash Models Arena UI Component Elo | 1311 |
| Design Arena | Gemini 3.7 Flash Models Arena Website Elo | 1315 |
Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for.
Token volume and request traffic to this model over time.
Drop-in code to call this model. OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. The only thing that changes between models is the model slug below.
Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step problem solving.
Gemini 3.7 Flash (batch) costs $0.375/M input tokens and $1.875/M output tokens, with separate rates for Cache Read at $0.0375/M tokens, Cache Write at $0.04167/M tokens, Image Input at $0.375/M tokens, Input Audio at $0.375/M tokens, Input Audio Cache at $0.0375/M tokens, and Web Search at $14.00/1K calls.
Gemini 3.7 Flash (batch) has a 1,048,576 token context window. It supports up to 65,536 completion tokens.
Yes. Gemini 3.7 Flash (batch) accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.
Gemini 3.7 Flash (batch) accepts text, images, video, files such as PDFs, and audio as input and returns text.
Gemini 3.8 Flash, Gemini 3.6 Flash, Gemini 3.5 Flash Lite and 24 more are other text models from Google.
Gemini 3.7 Flash (batch) was released on August 13, 2026.
